Comment by postalcoder
1 year ago
I wholly agree with you. I've been using every model extensively since early the Davincis and I strongly believe that gpt-4-0314 was the best model they've released to date.
It's poor performance on benchmarks drives my skepticism of LLM benchmarking in general. I trust my feel for the models much more, and my feel was that 0314 was great.
The one thing that 0314 doesn't do well are the tricks like structured output and tool calling which makes it a less useful agentic type of tool, but from a pure thinking perspective, I think it's the best.
That's my concern - they marked 4 as "legacy" in the GUI, and now they hid it temporarily under a submenu - but it's the only model I care about. If they remove it, there is no reason for me to use their services, especially with Claude 3.5 wider context window and reasonably good results.